INDEX

Explanations

proper nouns related to individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and titles related to individuals and roles

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 underwater

-0.60

 Myst

-0.60

Â·Â·

-0.59

 silent

-0.58

 tablets

-0.56

 mainland

-0.56

IBLE

-0.55

huh

-0.55

 vacant

-0.54

 Sphere

-0.54

POSITIVE LOGITS

enberg

1.16

zinski

1.16

zik

1.13

orf

1.11

reau

1.09

enburg

1.07

meyer

1.06

enh

1.05

ensen

1.05

eman

1.03

Activations Density 0.144%

proper nouns related to individuals

proper nouns, particularly names and titles related to individuals and roles

No Comments

No Known Activations